Commit graph

5 commits

Author SHA1 Message Date
119359c33d Reconcile the release record; guard the image pin with tests
The publication at b51d174 pinned the manifest and appended a note, but left
three documents asserting the opposite. docs/image-scan-2026-09-06.md said "It
has not been pushed" in its Outcome block at the top while recording the
successful push at the bottom; its "Release status" section still said no
release digest existed and the manifest carried REPLACE_WITH_RELEASE_DIGEST;
and deploy/README.md still instructed an operator to replace a placeholder that
is now a real digest -- an instruction to undo the pin.

This is the derived-artifact staleness this repo argued for a rule about in
v0.8 §12 and then produced in its own release evidence, in the file another
repository would read to confirm what shipped. Superseded sections are now
marked in place with what replaced them rather than deleted, since they record
why the base changed and why the release was held. The scan doc carries a
status marker naming which parts state current state, including that a clean
scan is point-in-time and ages as advisories are published.

The workplan gains the publication entry it never got, and a re-check of T03's
full acceptance: a published image reads like a finished task, but the digest
was one of five requirements. Nothing is deployed -- the namespace is empty and
no secrets exist -- and production serve refuses to start without authenticated
audit delivery, so a rollout today would fail closed and prove nothing. T03
stays wait on T01's registrations and the audit credential.

Also corrects an earlier caution in the workplan that the digest was "a local
image id, not a release digest". That was wrong: with the containerd/OCI store
the build id is the manifest digest, and the registry resolves it.

tests/test_deploy_manifest.py holds the pin mechanically instead of by review:
both image references exist, are digest-pinned rather than tagged, are
identical, and no placeholder remains. The identity check matters because the
init container migrates the database the server then serves -- two different
digests there is a split-brain migration. Verified the guard fails on the drift
it targets, not only that it passes today. 116 tests pass.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PM5HnEAhokxdfcPqBNpT7D

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 715850@bnt-lap001
Assistant-Session: eb557e93-7cb1-45d0-9e57-7d15b3edc60e
2026-09-07 09:04:34 +02:00
b51d174500 Pin published approval-engine release candidate
Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0726e-5232-73f2-aaca-2c05ceb62efb
2026-09-06 23:32:19 +02:00
6d18f62a90 Set the approval store tenant to exact tenant:platform
Operator decision 5ed3fb35-eca9-413a-82b9-95171ba85bf6 accepts tenant:platform
as the platform management, administration and services tenant, with no alias
to platform or tenant:coulomb and no implicit cross-tenant grant. This closes
the collision recorded in 5c87ba8, where the manifest served --tenant platform
while the requested registrations issued tenant:coulomb.

The store tenant is now exactly tenant:platform in the manifest, the CLI
default, and the Engine default, and the requested client registrations ask for
the same spelling. Exact JWT/store equality is retained: no mapping table, no
normalisation, no prefix handling.

Moving the defaults rather than only the manifest is deliberate. A default of
platform under a sanctioned value of tenant:platform is a trap, because a serve
that omits --tenant would come up healthy and then refuse every authenticated
call -- the exact failure this decision exists to prevent.

That default change broke ten tests whose identity fixtures hard-coded
platform. This is the hazard flex-auth reported as FLEX-DEC-2026-008: fixtures
that all carry one tenant prove nothing about the tenant field. Fixtures are
aligned to the exact spelling, and the field is now varied rather than merely
present. test_near_miss_tenant_spellings_are_forbidden refuses platform,
tenant:coulomb, case variants, whitespace variants and empty against a
tenant:platform store; test_exact_sanctioned_tenant_is_admitted pins the other
half so a reject-everything bug cannot pass it. 111 tests pass.

Also records the credential-independent half of the GLAS-WP-0015 image request:
the image builds non-root uid 10001 off the pinned base, carries schema v3 and
the new tenant default, migrates and verifies a fresh store to schema_version 3
with integrity ok, and refuses production without a persistent database or
authenticated audit delivery. No scan was run -- no scanner is installed here --
and no release digest exists, so T01 and T03 both stay open.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PM5HnEAhokxdfcPqBNpT7D

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 715850@bnt-lap001
Assistant-Session: eb557e93-7cb1-45d0-9e57-7d15b3edc60e
2026-09-06 22:33:50 +02:00
06544b0fb4 fix: align approval deployment endpoints with live KeyCape
Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0726e-5232-73f2-aaca-2c05ceb62efb
2026-09-06 19:45:40 +02:00
2bd2d19a98 Implement approval engine production readiness
Assistant: codex
Assistant-Model: gpt-5.6-sol
Assistant-Session: 01a05e2e-805b-7042-a750-71f473bceea2
2026-09-02 00:52:04 +02:00